Medical mask on cat for protection of Coronavirus Covid19 virus selective focus on eyes

(© evsafronov - stock.adobe.com)

GLASGOW, Scotland — Artificial intelligence may be the best hope humans have for finding the next virus jumping from animals to humans before it becomes a pandemic. Scientists from the University of Glasgow say a form of AI which analyzes viral genomes could predict and possibly stop the next pathogen which is ready to “jump” from other species into humans — like COVID-19.

The exact origins of COVID-19 are still unclear. However, most scientists agree that at some point SARS-CoV-2 jumped from an animal (like bats) to humans. While COVID’s outbreak is bringing the threat of animal-to-human disease transmission to the forefront of the conversation, the reality is that many infectious diseases in recent years originated within an animal before crossing over. Researchers say this is why identifying new high-risk zoonotic viruses before they have a chance to spread is so important.

Not every animal virus is a threat to humans

It’s no easy feat identifying animal viruses potentially capable of infecting humans. Estimates show there are 1.67 million animal viruses out there, but only a small portion are capable of infecting humans. So, in order to create AI models capable of using viral genome sequences, researchers put together a dataset of 861 virus species from 36 families.

From that point, the team constructed machine learning models which assigned a “human infection probability score” for each virus based on patterns in their genomes. Researchers used the top performing AI model to analyze patterns in the predicted zoonotic potential of additional virus genomes from various species.

That process led researchers to conclude that viral genomes may have generalizable features that “preadapt” these viruses to infect humans. Study authors then created more machine learning models capable of identifying specific viruses likely to infect humans via viral genomes.

‘Red flagging’ potential pandemics

While this work is very promising, the team concedes that their models do have limitations. They add using AI is just the first step in terms of identifying animal-based viruses which can pass to humans. Researchers say any viruses the models “red flag” should be subject to further lab tests.

Moreover, just because an animal virus may be able to infect human beings, that doesn’t necessarily mean the virus will actually prove especially harmful, or particularly contagious for that matter.

“Our findings show that the zoonotic potential of viruses can be inferred to a surprisingly large extent from their genome sequence. By highlighting viruses with the greatest potential to become zoonotic, genome-based ranking allows further ecological and virological characterization to be targeted more effectively,” the researchers write in a media release.

“These findings add a crucial piece to the already surprising amount of information that we can extract from the genetic sequence of viruses using AI techniques,” adds study co-author Simon Babayan.

“A genomic sequence is typically the first, and often only, information we have on newly-discovered viruses, and the more information we can extract from it, the sooner we might identify the virus’ origins and the zoonotic risk it may pose. As more viruses are characterized, the more effective our machine learning models will become at identifying the rare viruses that ought to be closely monitored and prioritized for preemptive vaccine development.”

The study appears in the journal PLoS Biology.

About John Anderer

Born blue in the face, John has been writing professionally for over a decade and covering the latest scientific research for StudyFinds since 2019. His work has been featured by Business Insider, Eat This Not That!, MSN, Ladders, and Yahoo!

Studies and abstracts can be confusing and awkwardly worded. He prides himself on making such content easy to read, understand, and apply to one’s everyday life.

Our Editorial Process

StudyFinds publishes digestible, agenda-free, transparent research summaries that are intended to inform the reader as well as stir civil, educated debate. We do not agree nor disagree with any of the studies we post, rather, we encourage our readers to debate the veracity of the findings themselves. All articles published on StudyFinds are vetted by our editors prior to publication and include links back to the source or corresponding journal article, if possible.

Our Editorial Team

Steve Fink

Editor-in-Chief

Chris Melore

Editor

Sophia Naughton

Associate Editor